Back

Involuntary breathing movement pattern recognition and classification via force based sensors.

Singh, R. E.; Fleury, J. M.; Gupta, S.; Bachman, N. P.; Alumbaugh, B.; White, G.

2022-07-14 bioengineering
10.1101/2022.07.12.499777 bioRxiv
Show abstract

The study presents a novel scheme that recognizes and classifies different sub-phases within the involuntary breathing movement (IBM) phase during breath-holding (BH). We collected force data from eight recreational divers until the conventional breakpoint (CB). They were in a supine position on force plates. We segmented their data into the no-movement (NM) phase aka easy phase and IBM phase (comprising several events or sub-phases of IBM). The acceleration and jerk were estimated from the data to quantify the IBMs, and phase portraits were developed to select and extract specific features. The K means clustering was performed on these features to recognize different sub-phases within the IBM phase. We found five-six optimal clusters separating different sub-phases within the IBM phase. These clusters separating different sub-phases have physiological relevance to internal struggle and were labeled as classes for classification using support vector machine (SVM), naive bayes (NB), decision tree (DT), and K-nearest neighbor (K-NN). In comparison with no feature selection and extraction, we found that our phase portrait method of feature selection and extraction had a low computational cost and high robustness of 96-99% accuracy.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.